Skip to content
conftrace_
2026 EMNLP EMNLP 2026

Query-Efficient Memory Injection Attacks on LLM Agents

AbstractLLM agents increasingly rely on persistent, shared memory, turning the memory module into a new attack surface through which attackers can inject malicious text via query-only interaction. Existing query-only attacks, however, remain expensive, requiring multiple bridging injected queries per target and leaving visible directive traces in stored records. We present AMIA (Agent Memory Injection Attack), which improves both query efficiency and stealth through three injection families along a stealth-to-effectiveness axis: prompt injection, semi-instruction that hides the misleading answer in a benign restate or discredit request, and no-instruction that delivers the false claim as the presupposition of a natural follow-up question. We progressively scale AMIA from QA agents on flat key-value memory, to multi-agent shared memory, and to three production-oriented memory architectures (Mem0, A-MEM, MemoryOS), and finally to three non-QA agent classes (clinical support, code summarization, web shopping), where AMIA exceeds prior query-only attacks on most settings while using a fraction of their inject query budget. We further evaluate defenses that mitigate all three attack families across settings. Our code is available at: https://github.com/TrustAIRLab/AMIA.

More from EMNLP 2026

All EMNLP 2026 papers →